15 papers
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
Yibo Li, Zijie Lin, Ailin Deng +5
While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforc…
AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
Yuexin Li, Wenjie Qu, Linyu Wu +5
Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable…
When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
Khoi Le, Tri Cao, Phong Nguyen +5
Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore,…
WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
Tri Cao, Yulin Chen, Hieu Cao +8
Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedd…
Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models
Tri Cao, Khoi Le, Thong Nguyen +7
While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We argue this stems from a failure i…
Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
Yuan Sui, Yufei He, Tri Cao +3
Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-train…